4 papers
The Price of Reasoning: Cost-Quality Tradeoffs in Reinforcement Learning for Neural Machine Translation
Michael Jungo, Aixiu An
Reinforcement learning with verifiable rewards (RLVR) has been established as a viable paradigm for the post-training of Large Language Models (LLMs), including downstream tasks, s…
Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning
Aixiu An, Michael Jungo, Eloi Eynard +4
Neural machine translation (NMT) in the legal domain is a linguistically and conceptually demanding task, primarily due to the complexity of legal language and the high level of pr…
Rule-Based Reinforcement Learning for Document Image Classification with Vision Language Models
Michael Jungo, Andreas Fischer
Rule-based reinforcement learning has been gaining popularity ever since DeepSeek-R1 has demonstrated its success through simple verifiable rewards. In the domain of document analy…
Zero-Shot Prompting and Few-Shot Fine-Tuning: Revisiting Document Image Classification Using Large Language Models
Anna Scius-Bertrand, Michael Jungo, Lars Vögtlin +2
Classifying scanned documents is a challenging problem that involves image, layout, and text analysis for document understanding. Nevertheless, for certain benchmark datasets, nota…